This constraint is open source. Any third-party models, product names, or trademarks referenced are the property of their respective owners, and Proto is not affiliated with them.
evo-design/proto-language/proto_language/constraint/sequence_composition/max_homopolymer_constraint.pyConstraint contributors
dguo8412
Penalize sequences containing homopolymers longer than specified maximum.
This constraint function identifies the longest homopolymer (consecutive run
of identical nucleotides or amino acids) in each sequence and penalizes
sequences where this exceeds a specified maximum length.
The penalty uses logarithmic scaling to provide graduated penalties: sequences
slightly over the limit receive moderate penalties, while sequences far
exceeding the limit receive strong penalties (capped at 1.0). This avoids
extreme penalty values while still strongly discouraging very long homopolymers.
dguo8412API Reference
Configuration for maximum homopolymer constraint.This class defines configuration parameters for limiting homopolymer length
in DNA, RNA, or protein sequences. Homopolymers are consecutive runs of the
same nucleotide or amino acid (e.g., “AAAAA”, “GGGGGG”, “SSSSSS”). This constraint
uses logarithmic scaling for penalties to avoid extreme values while still penalizing
very long homopolymers, providing moderate penalties for slightly exceeding the limit
and strong penalties for greatly exceeding the limit.
integer
required
Maximum allowed run of consecutive identical nucleotides or amino acids; longer runs are penalized.
ReturnsConstraintOutput
One result per sequence. A score of 0.0 indicates
no homopolymers exceed the maximum length (pass). Higher scores indicate
longer homopolymers with logarithmic scaling. metadata carries:max_homopolymer_length: Integer length of the longest homopolymer found in the sequence. For example, “ATCGAAAAAGTC” would have value 5 (for the “AAAAA” run).
Usage
Avoiding long A/T runs for DNA synthesis:python